🐦 Twitter Post Details

Viewing enriched Twitter post

@AhmedHAwadallah

Fara-7B is our first agentic small language model for computer use. We learned a lot, and looking forward to next steps: *Agentic models can be small, yet remain capable *Unlike solutions that rely on chat model wrappers, even small agentic models can process screenshots and perform direct GUI actions such as scrolling, typing, and clicking. *Simulation-driven multi-agent synthetic data to automates task generation, trajectory generation and validation is a way to address the agentic data scarcity gap, and in our case costs < $1 per task. *Evaluating CUA is hard ; we release WebTailBench, a new eval set with diverse tasks not found in other benchmarks, and work with an external party, Browserbase, to independently assessed Fara-7B using human annotators. Model available on Foundry and HuggingFace and can run on device on Copilot+ PC

Media 1

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1993036332810326442/media_0.jpg?",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1993036332810326442/media_0.jpg?",
      "type": "photo",
      "filename": "media_0.jpg"
    }
  ],
  "processed_at": "2025-11-27T21:02:44.674998",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "1993036332810326442",
  "url": "https://x.com/AhmedHAwadallah/status/1993036332810326442",
  "twitterUrl": "https://twitter.com/AhmedHAwadallah/status/1993036332810326442",
  "text": "Fara-7B is our first agentic small language model for computer use.\n\nWe learned a lot, and looking forward to next steps:\n\n*Agentic models can be small, yet remain capable\n\n*Unlike solutions that rely on chat model wrappers, even  small agentic models can process screenshots and perform direct GUI actions such as scrolling, typing, and clicking.\n\n*Simulation-driven multi-agent synthetic data to automates task  generation, trajectory generation and validation is a way to address the agentic data scarcity gap, and in our case costs < $1 per task.\n\n*Evaluating CUA is hard ; we release WebTailBench, a new eval set with diverse tasks not found in other benchmarks, and  work with an external party, Browserbase, to independently assessed Fara-7B using human annotators.\n\nModel available on Foundry and HuggingFace and can run on device on Copilot+ PC",
  "source": "Twitter for iPhone",
  "retweetCount": 27,
  "replyCount": 10,
  "likeCount": 119,
  "quoteCount": 2,
  "viewCount": 20547,
  "createdAt": "Mon Nov 24 19:17:45 +0000 2025",
  "lang": "en",
  "bookmarkCount": 62,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "1993036332810326442",
  "displayTextRange": [
    0,
    280
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "AhmedHAwadallah",
    "url": "https://x.com/AhmedHAwadallah",
    "twitterUrl": "https://twitter.com/AhmedHAwadallah",
    "id": "1103888904015364097",
    "name": "Ahmed Awadallah",
    "isVerified": false,
    "isBlueVerified": false,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1623116200975949824/b0ubd2D7_normal.jpg",
    "coverPicture": "",
    "description": "",
    "location": "",
    "followers": 1109,
    "following": 369,
    "status": "",
    "canDm": false,
    "canMediaTag": true,
    "createdAt": "Fri Mar 08 05:23:18 +0000 2019",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 398,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 13,
    "statusesCount": 167,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [],
    "profile_bio": {
      "description": "Working on AI agents, SLMs and post-training  @Microsoft | Partner Research Manager @Microsoft AI Frontiers",
      "entities": {
        "description": {
          "user_mentions": [
            {
              "id_str": "0",
              "indices": [
                46,
                56
              ],
              "name": "",
              "screen_name": "Microsoft"
            },
            {
              "id_str": "0",
              "indices": [
                84,
                94
              ],
              "name": "",
              "screen_name": "Microsoft"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "aka.ms/ahmed",
              "expanded_url": "https://aka.ms/ahmed",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/c3pt0XFcJM"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.twitter.com/EOZg7dKhsL",
        "expanded_url": "https://twitter.com/AhmedHAwadallah/status/1993036332810326442/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {},
          "orig": {}
        },
        "id_str": "1993034566920294400",
        "indices": [
          281,
          304
        ],
        "media_key": "3_1993034566920294400",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARuormEKW9AACgACG6iv/DGbUaoAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABG6iuYQpb0AAKAAIbqK/8MZtRqgAA",
            "media_key": "3_1993034566920294400"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/G6iuYQpb0AAjd23.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 1275,
              "w": 2276,
              "x": 0,
              "y": 0
            },
            {
              "h": 1448,
              "w": 1448,
              "x": 0,
              "y": 0
            },
            {
              "h": 1448,
              "w": 1270,
              "x": 0,
              "y": 0
            },
            {
              "h": 1448,
              "w": 724,
              "x": 0,
              "y": 0
            },
            {
              "h": 1448,
              "w": 2276,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1448,
          "width": 2276
        },
        "sizes": {
          "large": {
            "h": 1303,
            "w": 2048
          }
        },
        "type": "photo",
        "url": "https://t.co/EOZg7dKhsL"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {},
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "article": null
}